Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Breejen, Felix den, Bae, Sangmin, Cha, Stephen, Yun, Se-Young
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.13396
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929684294402048
author Breejen, Felix den
Bae, Sangmin
Cha, Stephen
Yun, Se-Young
author_facet Breejen, Felix den
Bae, Sangmin
Cha, Stephen
Yun, Se-Young
contents The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fine-tuning setting, resulting in a significant performance boost. We also discover that fine-tuning enables ICL-transformers to create complex decision boundaries, a property regular neural networks do not have. Based on this observation, we propose to pretrain ICL-transformers on a new forest dataset generator which creates datasets that are unrealistic, but have complex decision boundaries. TabForest, the ICL-transformer pretrained on this dataset generator, shows better fine-tuning performance when pretrained on more complex datasets. Additionally, TabForest outperforms TabPFN on some real-world datasets when fine-tuning, despite having lower zero-shot performance due to the unrealistic nature of the pretraining datasets. By combining both dataset generators, we create TabForestPFN, an ICL-transformer that achieves excellent fine-tuning performance and good zero-shot performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13396
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers
Breejen, Felix den
Bae, Sangmin
Cha, Stephen
Yun, Se-Young
Machine Learning
The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fine-tuning setting, resulting in a significant performance boost. We also discover that fine-tuning enables ICL-transformers to create complex decision boundaries, a property regular neural networks do not have. Based on this observation, we propose to pretrain ICL-transformers on a new forest dataset generator which creates datasets that are unrealistic, but have complex decision boundaries. TabForest, the ICL-transformer pretrained on this dataset generator, shows better fine-tuning performance when pretrained on more complex datasets. Additionally, TabForest outperforms TabPFN on some real-world datasets when fine-tuning, despite having lower zero-shot performance due to the unrealistic nature of the pretraining datasets. By combining both dataset generators, we create TabForestPFN, an ICL-transformer that achieves excellent fine-tuning performance and good zero-shot performance.
title Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers
topic Machine Learning
url https://arxiv.org/abs/2405.13396